NVIDIA / mellotron

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data
BSD 3-Clause "New" or "Revised" License
854 stars 184 forks source link

How can I speed up or slow down the output audio? #86

Open BabaiLi opened 3 years ago

BabaiLi commented 3 years ago

I didn't find the phonemes duration anywhere that I can speed up or slow down the output audio.

Does anyone know how to do?